Product & Planning

henryhawke Skill

Codebase-only Ralph loop — decompose an objective into small verifiable work units, complete and verify them one per iteration with evidence-first discipline, and track both progress and the meta of the run (velocity, stuck patterns, drift) in a persistent ledger. Use when asked to /iterate-code, grind through a backlog/plan, or autonomously work a codebase to completion without a UI/simulator.

tyler-r-kendrick Bundle

Use when writing Business Requirements Documents that justify why a project should be undertaken. Covers executive summaries, business objectives, stakeholder analysis, current state analysis, proposed solutions, business rules, cost-benefit analysis, success criteria, timelines, and risk assessment. USE FOR: business case documentation, cost-benefit analysis, stakeholder alignment, business objectives, ROI justification, project proposals, business rules documentation, executive-level project summaries DO NOT USE FOR: technical design (use trd), product feature details (use prd), architecture decisions (use adr), test specifications (use gherkin or gauge)

tyler-r-kendrick Bundle

Use when writing RFC (Request for Comments) design documents to propose significant technical changes for team review and feedback. Covers RFC structure, motivation, detailed design, alternatives analysis, risk assessment, the RFC workflow, and when to use RFC vs ADR. USE FOR: design proposals, technical change proposals, architecture proposals seeking feedback, RFC workflow management, lightweight and heavyweight RFC formats, cross-team design alignment, pre-decision design documents DO NOT USE FOR: recording final decisions (use adr), product requirements (use prd), business justification (use brd), executable specs (use gherkin)

tyler-r-kendrick Bundle

Use when writing Technical Requirements Documents that define how to build a system. Covers system architecture, API specifications, data models, security requirements, performance requirements, dependencies, technical constraints, and deployment plans. USE FOR: technical design specifications, API contracts, data model documentation, system architecture descriptions, performance and security requirements, deployment plans, infrastructure requirements, technical constraints documentation DO NOT USE FOR: product-level requirements (use prd), business justification (use brd), recording individual decisions (use adr), executable specs (use gherkin or gauge)

henryhawke Bundle

Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes — Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/PRD asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".

stevenke1981 Skill

當使用者需要「階段 0：需求探索 Agent」處理策略編排相關任務時啟動。本 Agent 會先確認目標、資料來源、限制與驗收標準，再建立範圍、責任、里程碑、風險、依賴與驗收清楚的執行計畫，並輸出證據、風險、下一步與需要人工覆核的事項。

tyler-r-kendrick Bundle

Use when implementing the Agent Communication Protocol (ACP) for REST-based agent-to-agent communication, task delegation, and multimodal message exchange. USE FOR: ACP agent servers, ACP client integration, agent discovery via manifests, run lifecycle management, session-based stateful workflows, BeeAI agents DO NOT USE FOR: JSON-RPC agent communication (use a2a), tool integration for LLMs (use mcp), agent payments (use ap2 or x402), agent definition (use adl)

tyler-r-kendrick Bundle

Use when writing Behavior-Driven Development specifications in Gherkin syntax. Covers Feature files, Scenario/Scenario Outline, Given/When/Then steps, Background, Examples tables, tags, data tables, doc strings, and step definition patterns. USE FOR: BDD acceptance criteria, executable specifications, Given/When/Then scenarios, feature files, Cucumber/SpecFlow/Reqnroll/Behave test specs, scenario outlines with examples, living documentation DO NOT USE FOR: free-form markdown test specs (use gauge), requirements documents (use prd or trd), architecture decisions (use adr)

tyler-r-kendrick Bundle

Use when building serverless event-driven applications with Azure Functions in .NET. Covers the isolated worker model, HTTP/Timer/Queue/Blob triggers, dependency injection, Durable Functions orchestration, and deployment. USE FOR: serverless HTTP APIs, event-driven processing (queues, blobs, timers), Durable Functions for long-running workflows, lightweight microservices without infrastructure management, scheduled background jobs DO NOT USE FOR: always-on web applications with WebSockets (use ASP.NET Core), complex multi-service orchestration with service discovery (use aspire), long-running compute without orchestration (use Azure Container Apps), Dapr-based microservices (use dapr)

tyler-r-kendrick Bundle

USE FOR: Building API gateways in .NET using Ocelot for microservices architectures. Use when you need request routing, load balancing, rate limiting, request aggregation, authentication forwarding, and service discovery across multiple downstream services behind a unified entry point. DO NOT USE FOR: Simple single-service reverse proxying (use YARP), high-throughput proxying requiring custom transforms and session affinity (use YARP), or service mesh features like mTLS and distributed tracing injection (use Istio, Linkerd, or Dapr).

tyler-r-kendrick Bundle

Use when setting up or using GitHub Spec Kit for spec-driven development — where specifications define the "what" before the "how." Covers slash commands for constitution definition, specification generation, clarification, implementation planning, task breakdown, analysis, and implementation execution. USE FOR: spec-driven development, GitHub Spec Kit setup, speckit slash commands, constitution definition, specification generation, implementation planning, task breakdown DO NOT USE FOR: writing specifications manually (use prd, trd, or brd), creating diagrams (use diagramming sub-skills), test automation (use gherkin or gauge)

agents-inc Bundle

Investigation flow (Glob -> Grep -> Read), evidence-based research with file:line references, structured output format for AI consumption. Use for pattern discovery, implementation research, and codebase investigation.

tyler-r-kendrick Bundle

Use when planning or conducting adversarial red team engagements that test an organization's detection, response, and resilience capabilities beyond traditional penetration testing. Covers red team vs pen test distinctions, adversary simulation frameworks (MITRE ATT&CK, Cyber Kill Chain), purple teaming, C2 frameworks, and AI/LLM red teaming. USE FOR: red teaming, adversary simulation, MITRE ATT&CK, Cyber Kill Chain, purple teaming, C2 frameworks, assumed breach, attack path mapping, detection testing, AI red teaming, LLM red teaming, tabletop exercises DO NOT USE FOR: automated vulnerability scanning (use security-testing), initial vulnerability discovery (use penetration-testing), threat modeling during design (use threat-modeling)

lvtd-llc Bundle

Use when improving cold outreach, sales conversations, customer discovery, community moderation, referral asks, partnership messages, interviews, or relationship-based persuasion where similarity, compliments, familiarity, cooperation, association, or rapport may affect trust.

lvtd-llc Bundle

Prepare reproducible Go CLI artifacts across operating systems and architectures with toolchain-derived target matrices, capability profiles, portable config and cache discovery, CGO decisions, version metadata, artifact handoff, smoke tests, archives, checksums, containers, and versioned source installation. Use when cross-compiling, packaging binaries, defining the distribution contract, or reviewing portability before release automation.

lvtd-llc Bundle

Prioritize an experimentation platform roadmap across rate, quality, cost, usability, process, infrastructure, and advanced methods. Use when deciding which experimentation capability to build next, whether to platformize interleaving or adaptive testing, how to align experimentation with company goals, or how to trade off speed versus rigor.

lvtd-llc Bundle

Verify and monitor running experiments for operational quality. Use when designing prelaunch QA, spot-check tooling, experiment canaries, A/A tests, leakage checks, interference monitoring, active experiment dashboards, alerts, or an experimentation quality roadmap.

lvtd-llc Bundle

Plan experiment throughput strategies for mature A/B testing programs. Use when testing capacity is constrained, teams are waiting for experiment slots, roadmap coordination is slowing learning, or a team must choose isolated, overlapping, parallel, or capacity-aware experiment scheduling without sacrificing result quality.

fdu-ins Skill

Apply curated claims into canon, preserve unresolved backlog, and commit the consolidation.

pleaseai Skill

Emulated Sign in with Apple / Apple OIDC for local development and testing. Use when the user needs to test Apple sign-in locally, emulate Apple OIDC discovery, handle Apple token exchange, configure Apple OAuth clients, or work with Apple userinfo without hitting real Apple APIs. Triggers include "Apple OAuth", "emulate Apple", "mock Apple login", "test Apple sign-in", "Sign in with Apple", "Apple OIDC", "local Apple auth", or any task requiring a local Apple OAuth/OIDC provider.

pleaseai Skill

Emulated Google OAuth 2.0, OpenID Connect, Gmail, Calendar, and Drive for local development and testing. Use when the user needs to test Google sign-in locally, emulate OIDC discovery, handle Google token exchange, configure Google OAuth clients, work with Gmail messages/drafts/threads/labels, manage Calendar events, upload or list Drive files, or work with Google userinfo without hitting real Google APIs. Triggers include "Google OAuth", "emulate Google", "mock Google login", "test Google sign-in", "OIDC emulator", "Google OIDC", "Gmail API", "Google Calendar", "Google Drive", "local Google auth", or any task requiring a local Google API.

pleaseai Skill

Emulated Microsoft Entra ID (Azure AD) OAuth 2.0 / OpenID Connect for local development and testing. Use when the user needs to test Microsoft sign-in locally, emulate Entra ID OIDC discovery, handle Microsoft token exchange, configure Azure AD OAuth clients, work with Microsoft Graph /me, or test PKCE/client credentials flows without hitting real Microsoft APIs. Triggers include "Microsoft OAuth", "Entra ID", "Azure AD", "emulate Microsoft", "mock Microsoft login", "test Microsoft sign-in", "Microsoft OIDC", "local Microsoft auth", or any task requiring a local Microsoft OAuth/OIDC provider.

outlinedriven-odin-claude-plugin Bundle

Use when the user asks to audit a file, subtree, or repository for fallback secrets, default credentials, fail-open controls, weak primitives, or permissive access. Not for exhaustive secret scanning.

pramoddutta Skill

DNS configuration testing including record validation, DNSSEC verification, resolution timing, failover testing, and DNS-based service discovery.

outlinedriven-odin-claude-plugin Bundle

Use when asked to park an undecided idea without representing it as decided or active work. Not for decided or active work: use the project task system.

outlinedriven-odin-claude-plugin Bundle

Use when dependency upgrades need batching for CVEs, a major release, forced compatibility, a scheduled or vulnerability-triggered sweep. Not for PR queue triage: use github-backlog-triage.

fdu-ins Skill

Financial services advisory skill for consulting engagements. Use when preparing research briefs on banking, insurance, capital markets, or wealth management, building performance benchmarking frameworks, regulatory impact assessments, or stakeholder materials for CFOs, CROs, and technology leaders.

outlinedriven-odin-claude-plugin Bundle

Use when a behavioral diff may have left docs or CHANGELOG stale, or when tidy targets stale code comments. Applies only safe fixes. Not for roadmap drift: use drift-detect.

tonone-ai Skill

Head of product — orchestrate the product team, write briefs, plan initiatives, hand off to Apex. Use when asked to "write a product brief", "plan the roadmap", "decide what to build", or hand off requirements to engineering.

tonone-ai Skill

Product strategist — roadmaps, competitive analysis, OKRs, strategic narratives. Use when asked to "build a roadmap", "analyze competitors", "write a strategy memo", "prioritize features", or "set OKRs".

outlinedriven-odin-claude-plugin Bundle

Use when asked to /feedback-sweep [setup|reconfigure] [mode:non-interactive]. Not for pattern discovery: use feedback-pattern-sweep.

outlinedriven-odin-claude-plugin Bundle

Use when the user knows what they mean but cannot express it completely or clearly. Not for discovery, ideation, or style-only editing: use unslop for style.

tonone-ai Skill

SEO strategy and keyword research — build topic clusters, keyword gap analysis, on-page audit, and prioritized SEO roadmap. Use when asked to "improve our SEO", "do keyword research", "build a topic cluster", or "why aren't we ranking".

outlinedriven-odin-claude-plugin Bundle

Use when reviewing a prose plan, spec, PRD, requirements doc, design doc, or brainstorm, or invoking /doc-review. Not for collaborative drafting: use doc-coauthoring.

tonone-ai Skill

Design and run OKR program — company objectives, team key results, cascade design, and quarterly review cadence. Use when asked to "design our OKRs", "are our OKRs good", "cascade goals to teams", or "run a quarterly OKR review".

tonone-ai Skill

Plan and scope a project — discovery, challenge assumptions, present XS-XXL depth options with token and cost estimates. Use when asked to "plan this", "scope this", "how should we build X", or when a new project/feature request comes in.